© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14880
    Prev
    Next
    INDEX
    Explanations

    api versioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    -2.63
     There
    -2.58
     because
    -2.53
     for
    -2.47
     by
    -2.44
     Even
    -2.42
     That
    -2.42
     At
    -2.38
     contributes
    -2.28
     promotes
    -2.27
    POSITIVE LOGITS
    2
    2.23
     delightfully
    2.14
     VERY
    2.09
    臯
    2.06
     magnific
    2.06
    providedIn
    2.06
     astonishing
    2.03
     REALLY
    2.03
    ౬
    2.03
     astounding
    2.02
    Activations Density 0.031%

    No Known Activations